© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104610
    Prev
    Next
    INDEX
    Explanations

    compound modifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     that
    -2.17
    ffilm
    -1.65
     Japão
    -1.53
     to
    -1.53
    𞤤
    -1.40
     outono
    -1.39
    pegawai
    -1.39
    呦
    -1.38
     suitably
    -1.38
    rowIndex
    -1.38
    POSITIVE LOGITS
    違います
    1.63
     решила
    1.59
     グッズ
    1.53
     each
    1.48
    iciais
    1.45
    Still
    1.42
     Gleaner
    1.41
     zkou
    1.39
    ściu
    1.39
    gencias
    1.39
    Activations Density 0.111%

    No Known Activations